Predicting student academic performance is linked to developing the best educational policies in higher education, which significantly impact economic and financial development. The wealth of readily available educational data makes it possible to address student issues, improve the learning environment, and make decisions based on data through the use of technology-enhanced learning platforms. It is impossible to evaluate a student's standing at a university without considering their academic performance. It allows academic staff, administrators, and decision-makers to evaluate students throughout a semester accurately. It also aids students in assessing their performance and improving it. This paper presents a comprehensive review of related studies on student academic performance. Several techniques have been reviewed, such as Support Vector Machine (SVM), Naïve Bayes (NB), Logistic Regression (LR), Decision Trees (DT), Extreme Learning Machine (ELM), Artificial Neural Network ANN, k-Nearest Neighbors (kNN), and ensemble methods such as Bagging, Random Forest (RF), and Adaptive Boosting (AB). In addition, student factors have been used and compared through different classifiers. Accordingly, the findings confirmed the usefulness of Neural Network as the most competitive classifier, and academic assessment was a prominent factor when predicting students’ academic performance.